summaryrefslogtreecommitdiffstats
path: root/net/mptcp
diff options
context:
space:
mode:
Diffstat (limited to 'net/mptcp')
-rw-r--r--net/mptcp/ctrl.c14
-rw-r--r--net/mptcp/pm_netlink.c7
-rw-r--r--net/mptcp/protocol.c67
-rw-r--r--net/mptcp/protocol.h1
4 files changed, 67 insertions, 22 deletions
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 54b888f94009..96ba616f59bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -18,6 +18,7 @@ struct mptcp_pernet {
struct ctl_table_header *ctl_table_hdr;
int mptcp_enabled;
+ unsigned int add_addr_timeout;
};
static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net)
return mptcp_get_pernet(net)->mptcp_enabled;
}
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+ return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
static struct ctl_table mptcp_sysctl_table[] = {
{
.procname = "enabled",
@@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = {
*/
.proc_handler = proc_dointvec,
},
+ {
+ .procname = "add_addr_timeout",
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_jiffies,
+ },
{}
};
static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
{
pernet->mptcp_enabled = 1;
+ pernet->add_addr_timeout = TCP_RTO_MAX;
}
static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
}
table[0].data = &pernet->mptcp_enabled;
+ table[1].data = &pernet->add_addr_timeout;
hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
if (!hdr)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 0d6f3d912891..446ef8f07734 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -232,7 +232,8 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
}
if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
- sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, timer,
+ jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
spin_unlock_bh(&msk->pm.lock);
@@ -264,6 +265,7 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
{
struct mptcp_pm_add_entry *add_entry = NULL;
struct sock *sk = (struct sock *)msk;
+ struct net *net = sock_net(sk);
if (lookup_anno_list_by_saddr(msk, &entry->addr))
return false;
@@ -279,7 +281,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
add_entry->retrans_times = 0;
timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
- sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX);
+ sk_reset_timer(sk, &add_entry->add_timer,
+ jiffies + mptcp_get_add_addr_timeout(net));
return true;
}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 88f2a7a0ccb8..eaa61e227492 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -466,6 +466,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
struct tcp_sock *tp;
u32 old_copied_seq;
bool done = false;
+ int sk_rbuf;
+
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+ if (unlikely(ssk_rbuf > sk_rbuf)) {
+ WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+ sk_rbuf = ssk_rbuf;
+ }
+ }
pr_debug("msk=%p ssk=%p", msk, ssk);
tp = tcp_sk(ssk);
@@ -528,7 +540,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
WRITE_ONCE(tp->copied_seq, seq);
more_data_avail = mptcp_subflow_data_available(ssk);
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
done = true;
break;
}
@@ -622,6 +634,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct mptcp_sock *msk = mptcp_sk(sk);
+ int sk_rbuf, ssk_rbuf;
bool wake;
/* move_skbs_to_msk below can legitly clear the data_avail flag,
@@ -632,12 +645,16 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
if (wake)
set_bit(MPTCP_DATA_READY, &msk->flags);
- if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
- move_skbs_to_msk(msk, ssk))
+ ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+ sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+ if (unlikely(ssk_rbuf > sk_rbuf))
+ sk_rbuf = ssk_rbuf;
+
+ /* over limit? can't append more skbs to msk */
+ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
goto wake;
- /* don't schedule if mptcp sk is (still) over limit */
- if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+ if (move_skbs_to_msk(msk, ssk))
goto wake;
/* mptcp socket is owned, release_cb should retry */
@@ -754,8 +771,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
if (!tcp_skb_can_collapse_to(skb))
return false;
- /* can collapse only if MPTCP level sequence is in order */
- return mpext && mpext->data_seq + mpext->data_len == write_seq;
+ /* can collapse only if MPTCP level sequence is in order and this
+ * mapping has not been xmitted yet
+ */
+ return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+ !mpext->frozen;
}
static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
@@ -833,19 +853,25 @@ static void mptcp_clean_una(struct sock *sk)
}
out:
- if (cleaned) {
+ if (cleaned)
sk_mem_reclaim_partial(sk);
+}
- /* Only wake up writers if a subflow is ready */
- if (mptcp_is_writeable(msk)) {
- set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags);
- smp_mb__after_atomic();
+static void mptcp_clean_una_wakeup(struct sock *sk)
+{
+ struct mptcp_sock *msk = mptcp_sk(sk);
- /* set SEND_SPACE before sk_stream_write_space clears
- * NOSPACE
- */
- sk_stream_write_space(sk);
- }
+ mptcp_clean_una(sk);
+
+ /* Only wake up writers if a subflow is ready */
+ if (mptcp_is_writeable(msk)) {
+ set_bit(MPTCP_SEND_SPACE, &msk->flags);
+ smp_mb__after_atomic();
+
+ /* set SEND_SPACE before sk_stream_write_space clears
+ * NOSPACE
+ */
+ sk_stream_write_space(sk);
}
}
@@ -1476,13 +1502,14 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk)
__mptcp_flush_join_list(msk);
do {
struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+ bool slowpath;
if (!ssk)
break;
- lock_sock(ssk);
+ slowpath = lock_sock_fast(ssk);
done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
- release_sock(ssk);
+ unlock_sock_fast(ssk, slowpath);
} while (!done);
if (mptcp_ofo_queue(msk) || moved > 0) {
@@ -1748,7 +1775,7 @@ static void mptcp_worker(struct work_struct *work)
long timeo = 0;
lock_sock(sk);
- mptcp_clean_una(sk);
+ mptcp_clean_una_wakeup(sk);
mptcp_check_data_fin_ack(sk);
__mptcp_flush_join_list(msk);
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 13ab89dc1914..278c88c405e8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -362,6 +362,7 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
}
int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
generated by cgit v1.2.3 (git 2.39.1) at 2024-09-21 17:55:55 +0000